检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Gazis, Alexandros Katsiri, Eleftheria Department of Electrical and Computer Engineering School of Engineering Democritus University of Thrace Xanthi67100 Greece Institute for the Management of Information Systems Athena Research & Innovation Center in Information Communication & Knowledge Technologies Marousi15125 Greece

This article introduces a novel middleware that utilizes cost-effective, low-power computing devices like Raspberry Pi to analyze data from wireless sensor networks (WSNs). It is designed for indoor settings like historical buildings and museums, tracking visitors and identifying points of interest. It serves as an evacuation aid by monitoring occupancy and gauging the popularity of specific areas, subjects, or art exhibitions. The middleware employs a basic form of the MapReduce algorithm to gather WSN data and distribute it across available computer nodes. Data collected by RFID sensors on visitor badges is stored on mini-computers placed in exhibition rooms and then transmitted to a remote database after a preset time frame. Utilizing MapReduce for data analysis and a leader election algorithm for fault tolerance, this middleware showcases its viability through metrics, demonstrating applications like swift prototyping and accurate validation of findings. Despite using simpler hardware, its performance matches resource-intensive methods involving audiovisual and AI techniques. This design’s innovation lies in its fault-tolerant, distributed setup using budget-friendly, low-power devices rather than resource-heavy hardware or methods. Successfully tested at a historical building in Greece (M. Hatzidakis’ residence), it is tailored for indoor spaces. This paper compares its algorithmic application layer with other implementations, highlighting its technical strengths and advantages. Particularly relevant in the wake of the COVID-19 pandemic and general monitoring middleware for indoor locations, this middleware holds promise in tracking visitor counts and overall building occupancy. © 2024, CC BY.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Smart Beds and Bedding Surfaces for Personalized Patient Care: A Review 6

Smart Beds and Bedding Surfaces for Personalized Patient Car...

引用

6th South-East Europe Design Automation, computer engineering, computer Networks and Social Media Conference, SEEDA-CECNSM 2021

作者： Karvounis, Evaggelos Polymeni, Sofia Tsipouras, Markos Koritsoglou, Kyriakos Tzovaras, Dimitrios Center for Research and Technology Hellas Information Technologies Institute Thessaloniki Greece Department of Electrical and Computer Engineering University of Western Macedonia Kozani Greece

ISBN: (纸本)9781665427425

Continuous patient monitoring during hospitalization is necessary to identify patterns of indicative risks or pathogens, whose early diagnosis and treatment is likely to lead to a reduction in morbidity and mortality and, consequently, a reduction in both the duration and cost of hospitalization. On the other hand, a patient falling from bed can cause serious damage to his health state, while the effect of pressure ulcers can be avoided by timely and accurate mapping of pressure points that inhibit tissue perfusion resulting in death. Recent technological advances and scientific achievements have introduced new and improved medical devices using highly-developed embedded control functions and interactivity. Current hospital beds include new forms of functionality, while still serving the same purpose. All of them are designed to fulfil a predefined purpose, whether that is to monitor the patient's vital signs continuously, in a non-obtrusive manner, or prevent a patient from falling off their bed or prevent the development of pressure ulcers. Over the last decades, this hospital bed evolution has brought a big change in both their standards and the overall patient care. In this work, we conduct a review of existing smart bed systems for patient monitoring, fall and pressure ulcer prevention from the state-of-the-art, focusing on evaluating smart bed systems that include any kind of smart features, like sensors and sensor mats, or exploiting Machine Learning (ML) algorithms and Wireless technology. © 2021 IEEE

关键词： Hospital beds

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Advertisement Design: A PIL-Based Approach for Quality and Performance Analysis

AI-Powered Advertisement Design: A PIL-Based Approach for Qu...

引用

Intelligent and Innovative technologies in Computing, electrical and Electronics (IITCEE), International Conference

作者： Harshitha Chilupuri G. Ramesh J. Praveen Venkataramaiah Gude Dept. of Artificial Intelligence and Machine Learning Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad India Dept. of Computer Science and Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad India Department of Electrical and Electronics Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad Telangana India GP Technologies LLC U.S.A.

ISBN: (数字)9798331515911

ISBN: (纸本)9798331515928

The paper presents the development of a Data Science solution that applies generative AI models in order to create high-quality images to be used in visual marketing and advertising. Using the Python library PIL (Pillow) along with machine learning frameworks, the solution combines predefined product images with the selected backgrounds, enhancing image synthesis techniques for more appealing and contextually relevant visuals. This leads to improved efficiency and effectiveness in the creation of content by automatically placing product images onto the background images used in marketing campaigns. The approach demonstrated a 98.06% SSIM (Structural similarity Index) score, indicating significant visual quality improvement. Initial results suggest a 15% enhancement in visual appeal compared to traditional image creation methods.

关键词： Visualization Image transformation Generative AI Data science Libraries Performance analysis Indexes Advertising Optimization Python

来源：评论

学校读者我要写书评

暂无评论

Unsupervised self-training for sentiment analysis of code-switched data

arXiv

引用

arXiv 2021年

作者： Gupta, Akshat Menghani, Sargam Rallabandi, Sai Krishna Black, Alan W. Department of Electrical and Computer Engineering Carnegie Mellon University Language Technologies Institute Carnegie Mellon University

Sentiment analysis is an important task in understanding social media content like customer reviews, Twitter and Facebook feeds etc. In multilingual communities around the world, a large amount of social media text is characterized by the presence of code-switching. Thus, it has become important to build models that can handle code-switched data. However, annotated code-switched data is scarce and there is a need for unsupervised models and algorithms. We propose a general framework called Unsupervised Self-Training and show its applications for the specific use case of sentiment analysis of code-switched data. We use the power of pre-trained BERT models for initialization and fine-tune them in an unsupervised manner, only using pseudo labels produced by zero-shot transfer. We test our algorithm on multiple code-switched languages and provide a detailed analysis of the learning dynamics of the algorithm with the aim of answering the question - ‘Does our unsupervised model understand the Code-Switched languages or does it just learn its representations?’. Our unsupervised models compete well with their supervised counterparts, with their performance reaching within 1-7% (weighted F1 scores) when compared to supervised models trained for a two class problem. Copyright © 2021, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

M2H2: A Multimodal Multiparty Hindi Dataset for Humor Recognition in Conversations 21

M2H2: A Multimodal Multiparty Hindi Dataset for Humor Recogn...

引用

23rd ACM International Conference on Multimodal Interaction, ICMI 2021

作者： Chauhan, Dushyant Singh Singh, Gopendra Vikram Majumder, Navonil Zadeh, Amir Ekbal, Asif Bhattacharyya, Pushpak Morency, Louis-Philippe Poria, Soujanya Department of Computer Science and Engineering Indian Institute of Technology Patna India Language Technologies Institute Carnegie Mellon University Pittsburgh United States Istd Singapore University of Technology and Design Singapore

ISBN: (纸本)9781450384810

Humor recognition in conversations is a challenging task that has recently gained popularity due to its importance in dialogue understanding, including in multimodal settings (i.e., text, acoustics, and visual). The few existing datasets for humor are mostly in English. However, due to the tremendous growth in multilingual content, there is a great demand to build models and systems that support multilingual information access. To this end, we propose a dataset for Multimodal Multiparty Hindi Humor (M2H2) recognition in conversations containing 6,191 utterances from 13 episodes of a very popular TV series "Shrimaan Shrimati Phir Se". Each utterance is annotated with humor/non-humor labels and encompasses acoustic, visual, and textual modalities. We propose several strong multimodal baselines and show the importance of contextual and multimodal information for humor recognition in conversations. The empirical results on M2H2 dataset demonstrate that multimodal information complements unimodal information for humor recognition. The dataset and the baselines are available at http://***/∼ai-nlp-ml/*** and https://***/declare-lab/M2H2-dataset. © 2021 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A blockchain-based privacy-preserving and access-control framework for electronic health records management

引用

Multimedia Tools and Applications 2024年第36期83卷 84195-84229页

作者： Jakhar, Amit Kumar Singh, Mrityunjay Sharma, Rohit Viriyasitavat, Wattana Dhiman, Gaurav Goel, Shubham Jaypee University of Information Technology Waknaghat Himachal Pradesh Solan173234 India Indian Institute of Information Technology Una Himachal Pradesh Saloh Una177209 India Business Information Technology Division Department of Statistics Faculty of Commerce and Accountancy Chulalongkorn University Bangkok Thailand School of Sciences and Emerging Technologies Jagat Guru Nanak Dev Punjab State Open University Patiala147001 India Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Centre of Research Impact and Outcome Chitkara University Punjab Rajpura140417 India Division of Research and Development Lovely Professional University Phagwara144411 India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun248002 India MEU research Unit Middle East University Amman Jordan

Healthcare data is crucial and sensitive, as it contains absolute information about a patient’s medical history, treatments, and actions;this information gets shared among the stakeholders on a routine basis. Patients’ information is vital and should be kept accurate, up-to-date, and secret;it should be available only to authorized users. Most of the existing systems are centralized and may breach data privacy. This study mainly focuses on protecting the privacy and security of sensitive healthcare data while sharing with multiple stakeholders. This work presents a privacy-preserving and access-control blockchain-based framework that uses consensus-driven decentralized data management on top of peer-to-peer distributed computing platforms to ensure the privacy, security, accessibility, and integrity of healthcare data. Blockchain technology helps to protect transactions from manipulation due to its features of irreversibility and immutability. Additionally, we thoroughly examine the security requirements afforded by blockchain-enabled systems by incorporating stakeholders like patients, doctors, chemists, and pathology labs as system entities;they can only share information through a proper channel. The proposed framework has been implemented and evaluated using Hyperledger Fabric. We observe that the proposed framework reveals promising benefits in security, regulation compliance, reliability, flexibility, and accuracy. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024. corrected publication 2024.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Four-dimensional conserved topological charge vectors in plasmonic quasicrystals

引用

Science (New York, N.Y.) 2025年第6734期387卷 644-648页

作者： Tsesses, Shai Dreher, Pascal Janoschka, David Neuhaus, Alexander Cohen, Kobi Meiler, Tim C. Bucher, Tomer Sapir, Shay Frank, Bettina Davis, Timothy J. Meyer Zu Heringdorf, Frank Giessen, Harald Bartal, Guy rew and Erna Viterbi Department of Electrical and Computer Engineering Technion - Israel Institute of Technology Haifa Israel Department of Physics MIT-Harvard Center for Ultracold Atoms and Research Laboratory of Electronics Massachusetts Institute of Technology Cambridge MA United States Faculty of Physics and Center for Nanointegration University of Duisburg-Essen Duisburg-Essen (CENIDE) Duisburg Germany 4th Physics Institute Research Center SCoPE Integrated Quantum Science and Technology Center University of Stuttgart Stuttgart Germany Centre for Disruptive Photonic Technologies and School of Physical and Mathematical Sciences Nanyang Technological University Singapore Faculty of Mathematics and Computer Science Weitzmann Institute of Science Rehovot Israel School of Physics University of Melbourne Parkville VIC Australia

According to Noether's theorem, symmetries in a physical system are intertwined with conserved quantities. These symmetries often determine the system topology, which is made ever more complex with increased dimensionality. Quasicrystals have neither translational nor global rotational symmetry, yet they intrinsically inhabit a higher-dimensional space in which symmetry resurfaces. Here, we discovered topological charge vectors in four dimensions (4D) that govern the real-space topology of 2D quasicrystals and reveal their inherent conservation laws. We demonstrate control over the topology in pentagonal plasmonic quasilattices, mapped by both phase-resolved and time-domain near-field microscopy, showing that their temporal evolution continuously tunes the 2D projections of their distinct 4D topologies. Our work provides a route to experimentally probe the thermodynamic properties of quasicrystals and topological physics in 4D and above.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep-sea Nodule Mineral Image Segmentation Algorithm Based on Pix2PixHD

引用

computers, Materials & Continua 2022年第10期73卷 1449-1462页

作者： Wei Song Haolin Wang Xinping Zhang Jianxin Xia Tongmu Liu Yuxi Shi School of Information and Engineering Minzu University of ChinaBeijing100081China Key Laboratory of Marine Environmental Survey Technology and Application Ministry of Natural ResourceGuangzhou510300China National Language Resource Monitoring&Research Center of Minority Languages Beijing100081China School of Ocean Science China University of GeosciencesBeijing100191China Department of Buoy Engineering South China Sea Marine Survey and Technology CenterGuangzhou510300China Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNew Jersey07102USA

Deep-sea mineral image segmentation plays an important role in deep-sea mining and underwater mineral resource monitoring and *** application of artificial intelligence technology to deep-sea mining projects can effectively improve the quality and efficiency of *** existing deep learning-based underwater image segmentation algorithms have problems such as the accuracy rate is not high enough and the running time is slightly *** order to improve the segmentation performance of underwater mineral images,this paper uses the Pix2PixHD(Pixel to Pixel High Definition)algorithm based on Conditional Generative Adversarial Network(CGAN)to segment deep-sea mineral *** model uses a coarse-to-fine generator composed of a global generation network and two local enhancement networks,and multiple multi-scale discriminators with same network structures but different input pictures to generate highquality *** test results on the deep-sea mineral datasets show that the Pix2PixHD algorithm can identify more target minerals under certain other *** evaluation index shows that the Pix2PixHD algorithm effectively improves the accuracy rate and the recall rate of deep-sea mineral image segmentation compared with the CGAN algorithm and the U-Net *** is important for expanding the application of deep learning techniques in the field of deep-sea exploration and mining.

关键词： Deep-sea mineral image segmentation generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

A Swarm-Based Distributed Algorithm for Target Encirclement with Application to Monitoring Tasks in Precision Agriculture Scenarios

A Swarm-Based Distributed Algorithm for Target Encirclement ...

引用

Mediterranean Conference on Control and Automation (MED)

作者： Giovanni de Carolis Ryan Williams Andrea Gasparri Department of Civil Computer Science and Aeronautical Technologies Engineering Roma Tre University Via della Vasca Navale 79 Roma Italy Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State University Blacksburg VA USA

This paper proposes a swarm-based approach for coordinating a multi-agent system (MAS) in a 3D environment to encircle a target for monitoring tasks in precision agriculture. Specifically, we are motivated by the objective of encircling large tree canopies in order to collaboratively gather information on tree health status. This goal is achieved by enhancing classical potential-based swarm design with a novel topology switching policy allowing the desired encirclement behavior to emerge. The resulting interaction protocol requires agents to utilize only local information, ensuring collision-free trajectories without restrictive assumptions on the undirected time-varying graph encoding the network topology. Numerical results are presented to demonstrate the effectiveness of the proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Overcome the Fear Of Missing Out: Active Sensing UAV Scanning for Precision Agriculture

arXiv

引用

arXiv 2023年

作者： Krestenitis, Marios Raptis, Emmanuel K. Kapoutsis, Athanasios Ch. Ioannidis, Konstantinos Kosmatopoulos, Elias B. Vrochidis, Stefanos Information Technologies Institute Centre for Research & Technology Hellas Thessaloniki57001 Greece Department of Electrical and Computer Engineering Democritus University of Thrace Xanthi67100 Greece

This paper deals with the problem of informative path planning for a UAV deployed for precision agriculture applications. First, we observe that the "fear of missing out" data lead to uniform, conservative scanning policies over the whole agricultural field. Consequently, employing a non-uniform scanning approach can mitigate the expenditure of time in areas with minimal or negligible real value, while ensuring heightened precision in information-dense regions. Turning to the available informative path planning methodologies, we discern that certain methods entail intensive computational requirements, while others necessitate training on an ideal world simulator. To address the aforementioned issues, we propose an active sensing coverage path planning approach, named OverFOMO, that regulates the speed of the UAV in accordance with both the relative quantity of the identified classes, i.e. crops and weeds, and the confidence level of such detections. To identify these instances, a robust Deep Learning segmentation model is deployed. The computational needs of the proposed algorithm are independent of the size of the agricultural field, rendering its applicability on modern UAVs quite straightforward. The proposed algorithm was evaluated with a simu-realistic pipeline, combining data from real UAV missions and the high-fidelity dynamics of AirSim simulator, showcasing its performance improvements over the established state of affairs for this type of missions. An open-source implementation of the algorithm and the evaluation pipeline is also available: https://***/emmarapt/OverFOMO. © 2023, CC BY.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：